Created by: shuxsu

我在代码中加入mask_rcnn.py中加入

spatial_scale = None if self.fpn is not None: body_feats, spatial_scale = self.fpn.get_output(body_feats) print("FPN网络输出的feature_map") fluid.layers.Print(body_feats)

出现错误信息

FPN网络输出的feature_map Traceback (most recent call last): File "train.py", line 342, in main() File "train.py", line 130, in main train_fetches = model.train(feed_vars) File "/home/aistudio/work/ppdet/modeling/architectures/mask_rcnn.py", line 292, in train return self.build(feed_vars, 'train') File "/home/aistudio/work/ppdet/modeling/architectures/mask_rcnn.py", line 101, in build fluid.layers.Print(body_feats) File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/layers/control_flow.py", line 200, in Print helper = LayerHelper('print' + "_" + input.name, **locals()) AttributeError: 'collections.OrderedDict' object has no attribute 'name'